mlsanityData to 7 Oct 2026

Visual Anomaly Detection for Images: A Survey

arXiv 2109.13157 ↗First posted 27 Sep 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Visual anomaly detection is an important and challenging problem in the field of machine learning and computer vision. This problem has attracted a considerable amount of attention in relevant research communities. Especially in recent years, the development of deep learning has sparked an increasing interest in the visual anomaly detection problem and brought a great variety of novel methods. In this paper, we provide a comprehensive survey of the classical and deep learning-based approaches for visual anomaly detection in the literature. We group the relevant approaches in view of their underlying principles and discuss their assumptions, advantages, and disadvantages carefully. We aim to help the researchers to understand the common principles of visual anomaly detection approaches and identify promising research directions in this field.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 38 of its 72 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

38 of 72 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2015Holistically-Nested Edge Detectioncited by 590
  9. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  10. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  11. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  12. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
26 more
  1. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  2. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  3. 2016Adversarial Feature Learningcited by 350
  4. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  5. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  6. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  7. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  8. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  9. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  10. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  11. 2018Residual Dense Network for Image Restorationcited by 181
  12. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  13. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  14. 2018Efficient GAN-Based Anomaly Detectioncited by 122
  15. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  16. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  17. 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
  18. 2018Learning Deep Features for One-Class Classificationcited by 76
  19. 2020Iterative energy-based projection on a normal data manifold for anomaly localizationcited by 47
  20. 2019One-Class Convolutional Neural Networkcited by 37
  21. 2020Learning to Incorporate Structure Knowledge for Image Inpaintingcited by 37
  22. 2019Deep Transfer Learning for Multiple Class Novelty Detectioncited by 33
  23. 2020Puzzle-AE: Novelty Detection in Images through Solving Puzzlescited by 23
  24. 2018AVID: Adversarial Visual Irregularity Detectioncited by 19
  25. 2020Self-Supervised Representation Learning for Visual Anomaly Detectioncited by 5
  26. 2017Spatial PixelCNN: Generating Images from Patchescited by 1

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 3; 2024: 1; 2025: 1.

11 papers.

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2022Diffusion Models for Medical Anomaly Detectioncited by 231
  3. 2022AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decodercited by 29
  4. 2023Unsupervised Pathology Detection: A Deep Dive Into the State of the Artcited by 24
  5. 2022A Survey of Visual Sensory Anomaly Detectioncited by 11
  6. 2022Learning to Identify Perceptual Bugs in 3D Video Gamescited by 5
  7. 2024Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakescited by 5
  8. 2023Feasibility of Universal Anomaly Detection without Knowing the Abnormality in Medical Imagescited by 3
  9. 2022Anomaly segmentation model for defects detection in electroluminescence images of heterojunction solar cellscited by 0
  10. 2023Image Outlier Detection Without Training using RANSACcited by 0
  11. 2025Latent Anomaly Detection: Masked VQ-GAN for Unsupervised Segmentation in Medical CBCTcited by 0